Meta-learning PINN loss functions

07/12/2021
by   Apostolos F Psaros, et al.
7

We propose a meta-learning technique for offline discovery of physics-informed neural network (PINN) loss functions. We extend earlier works on meta-learning, and develop a gradient-based meta-learning algorithm for addressing diverse task distributions based on parametrized partial differential equations (PDEs) that are solved with PINNs. Furthermore, based on new theory we identify two desirable properties of meta-learned losses in PINN problems, which we enforce by proposing a new regularization method or using a specific parametrization of the loss function. In the computational examples, the meta-learned losses are employed at test time for addressing regression and PDE task distributions. Our results indicate that significant performance improvement can be achieved by using a shared-among-tasks offline-learned loss function even for out-of-distribution meta-testing. In this case, we solve for test tasks that do not belong to the task distribution used in meta-training, and we also employ PINN architectures that are different from the PINN architecture used in meta-training. To better understand the capabilities and limitations of the proposed method, we consider various parametrizations of the loss function and describe different algorithm design options and how they may affect meta-learning performance.

READ FULL TEXT
research
01/30/2023

Online Loss Function Learning

Loss function learning is a new meta-learning paradigm that aims to auto...
research
03/10/2020

Learning State-Dependent Losses for Inverse Dynamics Learning

Being able to quickly adapt to changes in dynamics is paramount in model...
research
06/18/2023

Meta-Learning for Airflow Simulations with Graph Neural Networks

The field of numerical simulation is of significant importance for the d...
research
02/08/2020

ML-misfit: Learning a robust misfit function for full-waveform inversion using machine learning

Most of the available advanced misfit functions for full waveform invers...
research
11/29/2019

VIABLE: Fast Adaptation via Backpropagating Learned Loss

In few-shot learning, typically, the loss function which is applied at t...
research
12/04/2019

Learning to Recommend via Meta Parameter Partition

In this paper we propose to solve an important problem in recommendation...
research
05/15/2019

Addressing the Loss-Metric Mismatch with Adaptive Loss Alignment

In most machine learning training paradigms a fixed, often handcrafted, ...

Please sign up or login with your details

Forgot password? Click here to reset